Conference proceeding
Think Fast: Time Control in Varying Paradigms of Spiking Neural Networks
Proceedings of the International Conference on Neuromorphic Systems 2022, pp 1-8
27 Jul 2022
Abstract
The state-of-the-art in machine learning has been achieved primarily by deep learning artificial neural networks. These networks are powerful but biologically implausible and energy intensive. In parallel, a new paradigm of neural network is being researched that can alleviate some of the computational and energy issues. These networks, spiking neural networks (SNNs), have transformative potential if the community is able to bridge the gap between deep learning and SNNs. However, SNNs are notoriously difficult to train and lack precision in their communication. In an effort to overcome these limitations and retain the benefits of the learning process in deep learning, we investigate novel ways to translate between them. We construct several network designs with varying degrees of biological plausibility. We then test our designs on an image classification task and demonstrate our designs allow for a customized tradeoff between biological plausibility, power efficiency, inference time, and accuracy.
Metrics
8 Record Views
Details
- Title
- Think Fast: Time Control in Varying Paradigms of Spiking Neural Networks
- Creators
- Steven C. Nesbit - Drexel UniversityAndrew O'Brien - Drexel University, USAJocelyn Rego - Drexel UniversityGavin Parpart - Pacific Northwest National LaboratoryCarlos Gonzalez - Pacific Northwest National LaboratoryGarrett T. Kenyon - Los Alamos National LaboratoryEdward Kim - Drexel UniversityTerrence C. Stewart - National Research Council CanadaYijing Watkins - Pacific Northwest National LaboratoryACM
- Contributors
- Thomas E. Potok (Editor) - Oak Ridge National LaboratoryCatherine Schuman (Editor) - University of Tennessee at KnoxvilleMelika Payvand (Editor) - University of ZurichPrasanna Date (Editor) - Oak Ridge National LaboratoryShruti Kulkarni (Editor) - Oak Ridge National LaboratoryYiran Chen (Editor) - Duke UniversityRobinson Pino (Editor) - United States Department of EnergyBrad Aimone (Editor) - Sandia National LaboratoriesMutsumi Kimura (Editor) - Ryukoku UniversityGregory Cohen (Editor) - Western Sydney UniversityDavid Whittaker (Editor) - Elm Street VenturesGordon Hirsch Wilson (Editor) - Rain Neuromorphics
- Publication Details
- Proceedings of the International Conference on Neuromorphic Systems 2022, pp 1-8
- Conference
- ICONS: International Conference on Neuromorphic Systems
- Series
- ACM Other Conferences
- Publisher
- ACM
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science (Computing); College of Computing and Informatics
- Web of Science ID
- WOS:001089500800021
- Scopus ID
- 2-s2.0-85138416143
- Other Identifier
- 991021884692404721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Theory & Methods